[pve-devel] [PATCH qemu-server] fix #6207: vm status: cache last disk read/write values

[Fiona Ebner <f.ebner@proxmox.com>]

If disk read/write cannot be queried because of QMP timeout, they
should not be reported as 0, but the last value should be re-used.
Otherwise, the difference between that reported 0 and the next value,
when the stats are queried successfully, will show up as a huge spike
in the RRD graphs.

Invalidate the cache when there is no PID or the PID changed.

Signed-off-by: Fiona Ebner <f.ebner@proxmox.com>
---
 src/PVE/QemuServer.pm | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/src/PVE/QemuServer.pm b/src/PVE/QemuServer.pm
index f7f85436..5940ec38 100644
--- a/src/PVE/QemuServer.pm
+++ b/src/PVE/QemuServer.pm
@@ -2670,6 +2670,12 @@ our $vmstatus_return_properties = {
 
 my $last_proc_pid_stat;
 
+# See bug #6207. If disk write/read cannot be queried because of QMP timeout, they should not be
+# reported as 0, but the last value should be re-used. Otherwise, the difference between that
+# reported 0 and the next value, when the stats are queried successfully, will show up as a huge
+# spike.
+my $last_disk_stats = {};
+
 # get VM status information
 # This must be fast and should not block ($full == false)
 # We only query KVM using QMP if $full == true (this can be slow)
@@ -2741,6 +2747,14 @@ sub vmstatus {
         $d->{tags} = $conf->{tags} if defined($conf->{tags});
 
         $res->{$vmid} = $d;
+
+        if (
+            $last_disk_stats->{$vmid}
+            && (!$d->{pid} || $d->{pid} != $last_disk_stats->{$vmid}->{pid})
+        ) {
+            delete($last_disk_stats->{$vmid});
+        }
+
     }
 
     my $netdev = PVE::ProcFSTools::read_proc_net_dev();
@@ -2815,6 +2829,8 @@ sub vmstatus {
 
     return $res if !$full;
 
+    my $disk_stats_present = {};
+
     my $qmpclient = PVE::QMPClient->new();
 
     my $ballooncb = sub {
@@ -2862,8 +2878,10 @@ sub vmstatus {
 
             $res->{$vmid}->{blockstat}->{$drive_id} = $blockstat->{stats};
         }
-        $res->{$vmid}->{diskread} = $totalrdbytes;
-        $res->{$vmid}->{diskwrite} = $totalwrbytes;
+        $res->{$vmid}->{diskread} = $last_disk_stats->{$vmid}->{diskread} = $totalrdbytes;
+        $res->{$vmid}->{diskwrite} = $last_disk_stats->{$vmid}->{diskwrite} = $totalwrbytes;
+        $last_disk_stats->{$vmid}->{pid} = $res->{$vmid}->{pid};
+        $disk_stats_present->{$vmid} = 1;
     };
 
     my $machinecb = sub {
@@ -2925,7 +2943,13 @@ sub vmstatus {
 
     foreach my $vmid (keys %$list) {
         next if $opt_vmid && ($vmid ne $opt_vmid);
+
         $res->{$vmid}->{qmpstatus} = $res->{$vmid}->{status} if !$res->{$vmid}->{qmpstatus};
+
+        if (!$disk_stats_present->{$vmid} && $last_disk_stats->{$vmid}) {
+            $res->{$vmid}->{diskread} = $last_disk_stats->{$vmid}->{diskread};
+            $res->{$vmid}->{diskwrite} = $last_disk_stats->{$vmid}->{diskwrite};
+        }
     }
 
     return $res;
-- 
2.47.3



_______________________________________________
pve-devel mailing list
pve-devel@lists.proxmox.com
https://lists.proxmox.com/cgi-bin/mailman/listinfo/pve-devel